@Article{	  steffes_sasdelli_2026_platypus,
  title		= {Catch the Platypus! Negated Conditionals as a Challenge
		  for Machine Translation from Natural Language into Logical
		  Formalisms Using Large Language Models},
  url		= {https://ojs.bonviewpress.com/index.php/JCLLT/article/view/9092},
  doi		= {10.47852/bonviewJCLLT62029092},
  abstractnote	= {One of the most promising applications of large language
		  models in the legal domain concerns the automated
		  conversion of natural language legal texts into logical
		  formalisms, that is, automated formalization. Major
		  challenges to these approaches emerge from the semantic
		  fuzziness of natural language, which leads to sentences
		  that are particularly difficult to formalize—we call
		  these sentences “platypus sentences.” For example, the
		  natural negation of a sentence in natural language may have
		  different, context-dependent meanings, which often do not
		  correspond to the logical negation of a respective
		  formalization of said sentence. In other words, natural
		  negations and formalized negations often diverge from one
		  another. This problem is further intensified when
		  natural language conditionals (i.e., negated “if...
		  then...” sentences) are negated. The paper at hand
		  investigates how current large language models (GPT-5,
		  Llama, and LogicLinguist) deal with automated formalization
		  of negated conditionals. Our results indicate that
		  these systems still cannot reliably deliver correct
		  formalizations, although results can be enhanced, for
		  example, by prompt engineering.},
  journal	= {Journal of Computational Law and Legal Technology},
  author	= {Steffes, Bianca and Sasdelli, Diogo},
  year		= {2026},
  month		= {3},
  pages		= {1–7}
}